# RepVideo: Rethinking Cross-Layer Representation for Video Generation

arXiv: https://arxiv.org/abs/2501.08994 · HTML: https://mlsanity.com/paper/2501.08994/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- First posted on arXiv 15 Jan 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Built on by (most cited first, 12 of 12)

- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [Mixture of Contexts for Long Video Generation](https://mlsanity.com/paper/2508.21058/) (2025)
- [RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control](https://mlsanity.com/paper/2502.10059/) (2025)
- [WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World](https://mlsanity.com/paper/2512.10958/) (2025)
- [VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation](https://mlsanity.com/paper/2503.01739/) (2025)
- [PhysCorr: Dual-Reward DPO for Physics-Constrained Text-to-Video Generation with Automated Preference Selection](https://mlsanity.com/paper/2511.03997/) (2025)
- [Simulating the Visual World with Artificial Intelligence: A Roadmap](https://mlsanity.com/paper/2511.08585/) (2025)
- [Your One-Stop Solution for AI-Generated Video Detection](https://mlsanity.com/paper/2601.11035/) (2026)
- [Survey of Video Diffusion Models: Foundations, Implementations, and Applications](https://mlsanity.com/paper/2504.16081/) (2025)
- [ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos](https://mlsanity.com/paper/2503.16400/) (2025)
- [HumanSAM: Classifying Human-centric Forgery Videos in Human Spatial, Appearance, and Motion Anomaly](https://mlsanity.com/paper/2507.19924/) (2025)
- [Foveated Diffusion: Efficient Spatially Adaptive Image and Video Generation](https://mlsanity.com/paper/2603.23491/) (2026)

## Abstract (arXiv)

Video generation has achieved remarkable progress with the introduction of diffusion models, which have significantly improved the quality of generated videos. However, recent research has primarily focused on scaling up model training, while offering limited insights into the direct impact of representations on the video generation process. In this paper, we initially investigate the characteristics of features in intermediate layers, finding substantial variations in attention maps across different layers. These variations lead to unstable semantic representations and contribute to cumulative differences between features, which ultimately reduce the similarity between adjacent frames and negatively affect temporal coherence. To address this, we propose RepVideo, an enhanced representation framework for text-to-video diffusion models. By accumulating features from neighboring layers to form enriched representations, this approach captures more stable semantic information. These enhanced representations are then used as inputs to the attention mechanism, thereby improving semantic expressiveness while ensuring feature consistency across adjacent frames. Extensive experiments demonstrate that our RepVideo not only significantly enhances the ability to generate accurate spatial appearances, such as capturing complex spatial relationships between multiple objects, but also improves temporal consistency in video generation.